{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MI37PUJDHGPLYWPKMUFNLO4PIK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bbc7f12fbc3c6e9bfe0c8b4474f2cfe92f85c3c47fee3ef7e78224af30a76854","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T14:29:47Z","title_canon_sha256":"0ce4ec50948896567c7eadf5d361622c4c52639baf8f778b45c8bd997a24c12f"},"schema_version":"1.0","source":{"id":"2411.17465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17465","created_at":"2026-07-05T09:40:47Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17465v1","created_at":"2026-07-05T09:40:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17465","created_at":"2026-07-05T09:40:47Z"},{"alias_kind":"pith_short_12","alias_value":"MI37PUJDHGPL","created_at":"2026-07-05T09:40:47Z"},{"alias_kind":"pith_short_16","alias_value":"MI37PUJDHGPLYWPK","created_at":"2026-07-05T09:40:47Z"},{"alias_kind":"pith_short_8","alias_value":"MI37PUJD","created_at":"2026-07-05T09:40:47Z"}],"graph_snapshots":[{"event_id":"sha256:c45b8b91b2aa66d2c7b475e550d6f098a296667235461f97bf24b9b9c92eae76","target":"graph","created_at":"2026-07-05T09:40:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.17465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building Graphical User Interface (GUI) assistants holds significant promise for enhancing human workflow productivity. While most agents are language-based, relying on closed-source API with text-rich meta-information (e.g., HTML or accessibility tree), they show limitations in perceiving UI visuals as humans do, highlighting the need for GUI visual agents. In this work, we develop a vision-language-action model in digital world, namely ShowUI, which features the following innovations: (i) UI-Guided Visual Token Selection to reduce computational costs by formulating screenshots as an UI conne","authors_text":"Difei Gao, Kevin Qinghong Lin, Lijuan Wang, Linjie Li, Mike Zheng Shou, Shiwei Wu, Weixian Lei, Zechen Bai, Zhengyuan Yang","cross_cats":["cs.AI","cs.CL","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T14:29:47Z","title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17465","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:79b2392f695102a5dc1d71e04041c0a47c1598120159a80b85f24c50f9698f96","target":"record","created_at":"2026-07-05T09:40:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bbc7f12fbc3c6e9bfe0c8b4474f2cfe92f85c3c47fee3ef7e78224af30a76854","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T14:29:47Z","title_canon_sha256":"0ce4ec50948896567c7eadf5d361622c4c52639baf8f778b45c8bd997a24c12f"},"schema_version":"1.0","source":{"id":"2411.17465","kind":"arxiv","version":1}},"canonical_sha256":"6237f7d123399ebc59ea650ad5bb8f42b0930dcccda5f03d7563a3a7e1b9d52b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6237f7d123399ebc59ea650ad5bb8f42b0930dcccda5f03d7563a3a7e1b9d52b","first_computed_at":"2026-07-05T09:40:47.575024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:47.575024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aYSmVkqUg2gFMDD4M3PRUil5a5y5Q5o01PG82/fzSZZqw3+Up9cCLbDrUGMivdTw5VeKsHJTjtAtTvyc8wYGBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:47.575440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79b2392f695102a5dc1d71e04041c0a47c1598120159a80b85f24c50f9698f96","sha256:c45b8b91b2aa66d2c7b475e550d6f098a296667235461f97bf24b9b9c92eae76"],"state_sha256":"0d6cdb472530c456a67542ecd6199fd61367775697e58c754f3c3349c64cf6eb"}